Adversarial Open Set Domain Adaptation Based on Mutual Information

Domain adaptation focuses on utilizing a labeled source domain to classify an unlabeled target domain. Until recently domain adaptation setting was attributed to have only shared label space across both domains. However, this setting/assumption does not fit the real-world scenarios where the target domain may contain label sets that are absent in the source domain. This circumstance paved the way for the Open Set Domain Adaptation (OSDA) setting that supports the availability of unknown classes in the domain adaptation setting and demands the domain adaptation model to classify the unknown classes as an unknown class besides the shared/known classes. Negative transfer is a critical issue in open set domain adaptation, which stems from a misalignment of known/unknown classes before/during adaptation. Current open set domain adaptation methods lack at handling negative transfers due to faulty known-unknown class separation modules. To this end, we propose a novel approach to OSDA, Domain Adaptation based on Mutual Information (DAMI). DAMI leverages the optimization of Mutual Information to increase shared information between known-known samples and decrease shared information between known-unknown samples. A weighting module utilizes the shared information optimization to execute coarse-to-fine separation of known and unknown samples and simultaneously assists the adaptation of known samples. The weighting module limits negative transfer by step-wise evaluation and verification. DAMI is extensively evaluated on several benchmark domain adaptation datasets. DAMI is robust to various openness levels, performs well across significant domain gaps, and remarkably outperforms contemporary domain adaptation methods.